Exa is building a search engine from scratch to serve every AI application. We build massive-scale infrastructure to crawl the web, train state-of-the-art embedding models to index it, and develop super high performant vector databases in rust to search over it. We also own a $5m H200 GPU cluster and routinely run batchjobs with 10s of thousands of machines. This isn't your average startup :)
Our Agentic Search Team is building high-compute search to handle the most complex searches. These searches might run for minutes, hours, or even days. We're pretty flexible on what projects people work on based on their skills and interests.
You may be a good fit if you:
Have meaningful experience designing and scaling backend systems that handle high throughput and compute-intensive workloads
Strong coding skills in Typescript, Python, Go, Java, or similar languages
Own problems end-to-end, and are willing to pick up whatever knowledge you're missing to get the job done
You care about the problem of finding high quality information and are excited to build systems that enable true agentic reasoning over the world’s knowledge
Example Projects
Build orchestration pipelines for autonomous agents that plan, filter, and synthesize multi-step searches
Develop query planning, caching, and distributed execution systems that deliver reasoning-heavy results in near real time over billions of documents
Beat OpenAI's deep research using our search under the hood
This is an in-person opportunity in San Francisco. We're happy to sponsor international candidates (e.g., STEM OPT, OPT, H1B, O1, E3).
Top Skills
What We Do
Exa was built with a simple goal — to organize all knowledge. After several years of heads-down research, we developed novel representation learning techniques and crawling infrastructure so that LLMs can intelligently find relevant information.
